Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
Wolfram Language Image Identification Project launched an Image Identify site demo which returns the top predicted tags for the photos.
How does it work, briefly? I mean what type of learning vision technologies are used to analyze, recognize and understand the content of an image?
The ImageIdentify project uses the highly automated "superfunctions" and as part of Wolfram Language API integration. It relies on a complex collection of meta-algorithms and built-in 'knowledge'. It has a built-in classifier trained from a large dataset using Wolfram Data Framework (WDF). However the main classifier is based on the deep neural networks.
Source: How the Wolfram Language Image Identification Project Works
The algorithm isn't perfect and misidentification are more likely to be caused by 'irrelevant objects repeatedly being in training images for a particular type of object'.
You can read more at Wolfram Language Artificial Intelligence: The Image Identification Project.
